Skip to content

Instantly share code, notes, and snippets.

@AurelianTactics

AurelianTactics/bcq_actor.py

Created July 18, 2019 14:44
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save AurelianTactics/fa62bcc5c3ce1f457ce60884d8c315e6 to your computer and use it in GitHub Desktop.
Save AurelianTactics/fa62bcc5c3ce1f457ce60884d8c315e6 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
bcq_actor.py
self.fc1_actor_ = tf.contrib.layers.fully_connected(tf.concat([self.state_, self.action_], axis=1), actor_hs_list[0], activation_fn=tf.nn.relu) #400
self.fc2_actor_ = tf.contrib.layers.fully_connected(self.fc1_actor_, actor_hs_list[1], activation_fn=tf.nn.relu)
self.fc3_actor_ = tf.contrib.layers.fully_connected(self.fc2_actor_, action_dim, activation_fn=tf.nn.tanh) * 0.05 * max_action
self.actor_clip_ = tf.clip_by_value((self.fc3_actor_ + self.action_),-max_action, max_action)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment